The present disclosure involves systems, software, and computer-implemented methods for automatically predicting a probability of success or failure of change requests for an organization's information technology (IT) infrastructure or use environment. One example system includes at least one repository storing information corresponding to one or more prior change requests, at least one memory storing instructions and at least one prediction tool, and at least one hardware processor. Each change request corresponds to a request for a modification to one or more sections of the infrastructure. The instructions instruct the at least one hardware processor to receive one or more parameters corresponding to a new change request associated with the infrastructure. The parameters are provided as input to the at least one prediction tool, and in response, a probability of success of the new change request is received as an output of the at least one prediction tool.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
6. The system of claim 1, wherein the output of the at least one prediction tool further comprises one or more recommendations for modifying the new change request.
A system for managing software development processes includes a prediction tool that analyzes new change requests to identify potential risks or issues. The system evaluates the change request against historical data, codebase metrics, and other relevant factors to generate predictions about the impact of implementing the change. These predictions may include estimates of development time, risk levels, or compatibility issues. Additionally, the system provides recommendations for modifying the change request to mitigate identified risks or improve efficiency. The recommendations may suggest alternative approaches, code refactoring, or additional testing steps to ensure smoother integration. The system integrates with existing development workflows, allowing developers to receive real-time feedback and guidance when submitting or reviewing change requests. By leveraging predictive analytics, the system helps teams make informed decisions, reduce errors, and streamline the development process. The recommendations are tailored to the specific context of the change request, ensuring practical and actionable advice. This approach enhances collaboration and improves the overall quality of software releases.
7. The system of claim 6, wherein the one or more recommendations for modifying the new change request comprises recommendations for modifying at least one of the one or more parameters, or modifying one or more tasks to be performed to effect the requested modification associated with the new change request.
14. The system of claim 1, wherein the at least one prediction tool includes a machine learning algorithm that is one of an artificial neural network, or a decision tree model having one or more of feature importance or gradient boosting.
This invention relates to predictive systems that use machine learning algorithms to analyze data and generate predictions. The system addresses the challenge of accurately forecasting outcomes in complex datasets by employing advanced machine learning techniques to improve prediction accuracy and reliability. The system includes at least one prediction tool that utilizes a machine learning algorithm. The algorithm can be an artificial neural network, which processes data through interconnected layers to identify patterns and make predictions. Alternatively, the algorithm may be a decision tree model, which splits data into branches based on feature importance or gradient boosting. Gradient boosting enhances prediction accuracy by sequentially correcting errors from previous models, while feature importance helps identify the most influential variables in the dataset. The system is designed to handle diverse datasets and adapt to different prediction tasks, such as classification, regression, or anomaly detection. By leveraging these machine learning techniques, the system aims to provide more precise and actionable insights compared to traditional statistical methods. The use of neural networks and decision trees with gradient boosting ensures robustness and scalability, making the system suitable for applications in finance, healthcare, manufacturing, and other industries where predictive analytics is critical.
17. The non-transitory computer-readable medium of claim 15, wherein the at least one prediction tool includes a machine learning algorithm that is one of an artificial neural network, or a decision tree model having one or more of feature importance or gradient boosting.
This invention relates to a computer-implemented system for predictive modeling, specifically addressing the challenge of accurately forecasting outcomes using machine learning techniques. The system employs at least one prediction tool, which may include a machine learning algorithm such as an artificial neural network or a decision tree model. The decision tree model may incorporate feature importance or gradient boosting to enhance predictive accuracy. The system is designed to process input data, apply the selected machine learning algorithm, and generate predictions based on the learned patterns. The use of advanced machine learning models like neural networks or decision trees with feature importance or gradient boosting allows the system to handle complex datasets and improve prediction reliability. The invention is particularly useful in applications requiring high-accuracy forecasting, such as financial analysis, healthcare diagnostics, or industrial process optimization. The non-transitory computer-readable medium stores instructions for executing the predictive modeling process, ensuring reproducibility and scalability of the system. The system's flexibility in selecting different machine learning algorithms enables adaptation to various problem domains while maintaining robust predictive performance.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 3, 2019
November 22, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.